Triple
T19352367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jens Steube |
E484053
|
entity |
| Predicate | softwareProject |
P25429
|
FINISHED |
| Object | cudaHashcat |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: cudaHashcat | Statement: [Jens Steube, softwareProject, cudaHashcat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: cudaHashcat Context triple: [Jens Steube, softwareProject, cudaHashcat]
-
A.
Hashcat
chosen
Hashcat is a high-performance, open-source password recovery and cracking tool that supports numerous hashing algorithms and leverages GPU acceleration for speed.
-
B.
Equihash
Equihash is a memory-hard, proof-of-work hashing algorithm designed to be ASIC-resistant and used in cryptocurrencies such as Zcash.
-
C.
GHASH
GHASH is a polynomial-based universal hash function used within Galois/Counter Mode (GCM) to provide efficient message authentication over binary fields.
-
D.
John the Ripper
John the Ripper is a widely used open-source password cracking tool designed for security auditing and penetration testing.
-
E.
SipHash24
SipHash24 is a fast, cryptographically secure keyed hash function designed to protect hash tables from collision attacks while remaining efficient for short inputs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69d8e8d244f8819080eb1f3491300db2 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e61905b16881909ab0e932bb9a0cda |
completed | April 20, 2026, 12:16 p.m. |
Created at: April 10, 2026, 1:34 p.m.